Provider Capabilities
Feature support by provider and tier. Unsupported modifiers return 400.
Capability Matrix
| Provider | Tier | SSML | Markup | Speed | Multi-Speaker | Model Selection | Prompt | Bitrate Config |
|---|---|---|---|---|---|---|---|---|
| Google[1] | Premium | Conditional | Conditional | Conditional | No | No | No | Yes |
| Google[2] | Ultra | Yes | No | No | Conditional | Yes | Yes | Yes |
| Polly | Premium | Yes | No | No | No | No | No | No |
| Polly | Ultra | Yes | No | No | No | No | No | No |
| Kokoro | Premium | No | No | Yes | No | No | No | Yes |
| Azure[3] | Premium | Conditional | No | Conditional | No | No | No | Conditional |
| Azure[4] | Ultra | Conditional | No | Conditional | No | No | No | Conditional |
[1] SSML, markup, and speed vary by voice family — check GET /api/v1/voices.
[2] Multi-speaker and text limits vary by selected model — see Google Ultra Model Details.
[3] Long-form speech is available for every selectable Azure voice. Formats and delivery settings vary by voice.
[4] Long-form speech is available for every selectable Azure voice. Formats and delivery settings vary by voice.
Models By Tier
These are the public voice families you will see in GET /api/v1/voices, grouped by provider and tier.
| Provider | Tier | Models |
|---|---|---|
| Premium | Casual, Chirp-HD, Chirp3-HD, Neural2, News, Polyglot, Standard, Studio, Wavenet | |
| Ultra | Gemini 2.5 Flash TTS, Gemini 2.5 Pro TTS, Gemini 2.5 Flash Lite Preview TTS, Gemini 3.1 Flash TTS Preview, Gemini 3.8 Flash TTS, Gemini 3.8 Flash Lite TTS | |
| Polly | Premium | Generative, Neural, Standard |
| Polly | Ultra | Long-Form |
| Kokoro | Premium | Kokoro |
| Azure | Premium | Dragon HD Flash, Dragon Latest, MAI Voice 1, MAI Voice 2 Flash, MAI Voice 2.1 Flash, Multilingual Neural, OpenAI Neural, Standard Neural |
| Azure | Ultra | Dragon HD, Dragon HD Omni, MAI Voice 2, MAI Voice 2.1, OpenAI Neural HD |
Looking for supported languages and live voice availability? Browse the Voice Library for a visual view, or use GET /api/v1/voices for the full API response. For per-voice capability discovery (streaming, formats, limits, speed, prompt), use GET /api/v1/voices/{voice_id}.
Text And Prompt Limits
The limits below show the maximum accepted text for each provider and tier, plus prompt limits where prompt is supported. Google Ultra limits vary by selected model.
| Provider | Tier | Max Text(bytes) | Streaming Max(bytes) | Prompt Limits(bytes) |
|---|---|---|---|---|
| Premium | 500,000 | 5,000 | Not supported | |
| Ultra | Varies by model | Varies by model | Varies by model | |
| Polly | Premium | 100,000 | 3,000 | Not supported |
| Polly | Ultra | 100,000 | 3,000 | Not supported |
| Kokoro | Premium | 5,000 | 5,000 | Not supported |
| Azure | Premium | 500,000 | 4,000 | Not supportedOriginal UTF-8 input bytes, including SSML tags and whitespace. |
| Azure | Ultra | 500,000 | 4,000 | Not supportedOriginal UTF-8 input bytes, including SSML tags and whitespace. |
When prompt is used, chars_charged includes both text and prompt bytes.
Google Ultra Model Details
Google Ultra limits vary by selected model. Use the model field in your request to select a specific model.
| Model | Max Text | Stream Max | Prompt Max | Combined Max | Multi-Speaker |
|---|---|---|---|---|---|
| Flash TTSgemini-2.5-flash-tts | 4,000 | 4,000 | 4,000 | 8,000 | Yes |
| Pro TTSgemini-2.5-pro-tts | 4,000 | 4,000 | 4,000 | 8,000 | Yes |
| Flash Lite Previewgemini-2.5-flash-lite-preview-tts | 300 | 300 | 300 | 300 | No |
| 3.1 Flash TTS Previewgemini-3.1-flash-tts-preview | 4,000 | 4,000 | 4,000 | 8,000 | Yes |
| 3.8 Flash TTSgemini-3.8-flash-tts | 4,000 | 4,000 | 4,000 | 8,000 | Yes |
| 3.8 Flash Lite TTSgemini-3.8-flash-lite-tts | 4,000 | 4,000 | 4,000 | 8,000 | Yes |
Flash Lite Preview is a reduced-capacity preview model best suited for very short text. Use Flash TTS or Pro TTS for longer content.
Voice-Level Capabilities
The matrix above covers provider/tier-level features. For voice-specific capabilities, use GET /api/v1/voices. Each voice includes:
| Field | Description |
|---|---|
| supports_ssml | Whether this voice supports SSML input format |
| supports_markup | Whether this voice supports markup input format |
| supports_multispeaker | Whether this voice supports multi-speaker mode |
| model_type | Voice tier: "premium" or "ultra" |
| language | Voice language code (e.g., en-US) |
| provider | Voice provider (e.g., google, polly, kokoro) |
| available_models | Available ultra model IDs for this voice (ultra voices with model selection only) |
Always check voice-level fields before sending optional modifiers. See GET /api/v1/voices for the full response shape.
Output Formats
The async API (POST /api/v1/tts) supports three output formats, Provider and family support varies. Set output_format in your request (default: wav).
| Format | Sample Rates | Bitrate Range | Default Bitrate | Notes |
|---|---|---|---|---|
| wav | 8k–48k | — | — | Uncompressed PCM. Largest files, no bitrate setting. |
| mp3 | 8k–48k | 32–320 kbps | 128 kbps | Widest playback compatibility. |
| ogg_opus | 8k, 12k, 16k, 24k, 48k | 6–320 kbps | 64 kbps | Best quality-to-size ratio. |
Bitrate is configurable for Google, Kokoro, and Azure (output_bitrate_kbps). Other providers manage bitrate internally. Use sample_rate_hertz to control sample rate for any format.
Streaming Delivery
Short-form generation supports streaming delivery. In the web app, use Stream Preview in the advanced settings on /tts. For the public API, use POST /api/v1/tts/stream. Every streaming request creates a normal job with the same billing and storage behavior as async generation. If matching audio is already available, the service returns the completed result immediately instead of opening a new live stream. Streaming is short-form only. Maximum text length varies by provider. See the Streaming Max column in the Text and Prompt Limits table.
| Provider | Tier | Family | Streaming | Default Transport | Supported Formats (API v1) | Bitrates | Notes |
|---|---|---|---|---|---|---|---|
| Premium | Chirp3HD | Yes | ogg_opus | ogg_opus (24k/48k), wav (24k/48k), pcm (24k/48k), mulaw (8k), alaw (8k) | not available | Max speaking rate: 2.0 | |
| Premium | ChirpHD | Yes | ogg_opus | ogg_opus (24k/48k), wav (24k/48k), pcm (24k/48k), mulaw (8k), alaw (8k) | not available | Max speaking rate: 2.0 | |
| Premium | Wavenet | No | — | — | not available | not available | |
| Premium | Neural2 | No | — | — | not available | not available | |
| Premium | Studio | No | — | — | not available | not available | |
| Premium | Standard | No | — | — | not available | not available | |
| Premium | Casual | No | — | — | not available | not available | |
| Premium | Polyglot | No | — | — | not available | not available | |
| Premium | News | No | — | — | not available | not available | |
| Ultra | Gemini TTS | Yes | wav | wav (24k), pcm (24k) | not available | Speaking rate not supported; Gemini 3.8: 132 Flash and 103 Flash Lite language/script rows. Hausa: Flash and Flash Lite. Swahili: Flash only. Language support does not promise regional accents or preview availability. | |
| Polly | Premium | Standard | Yes | ogg_opus | ogg_opus (48k), mp3 (8k–24k), wav (8k/16k), ogg_vorbis (8k–24k), pcm (8k/16k), mulaw (8k), alaw (8k) | not available | not available |
| Polly | Premium | Neural | Yes | ogg_opus | ogg_opus (48k), mp3 (8k–24k), wav (8k/16k), ogg_vorbis (8k–24k), pcm (8k/16k), mulaw (8k), alaw (8k) | not available | not available |
| Polly | Premium | Generative | Yes | ogg_opus | ogg_opus (48k), mp3 (8k–24k), wav (8k/16k), ogg_vorbis (8k–24k), pcm (8k/16k), mulaw (8k), alaw (8k) | not available | not available |
| Polly | Ultra | Long-Form | Yes | ogg_opus | ogg_opus (48k), mp3 (8k–24k), wav (8k/16k), ogg_vorbis (8k–24k), pcm (8k/16k), mulaw (8k), alaw (8k) | not available | not available |
| Kokoro | Premium | Kokoro | Yes | ogg_opus | ogg_opus (24k), mp3 (24k), wav (24k), pcm (24k) | not available | not available |
| Azure | Premium | Standard Neural | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: Neural. Long form: Available for all selectable voices. |
| Azure | Premium | Multilingual Neural | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: Multilingual. Long form: Available for all selectable voices. |
| Azure | Ultra | Dragon HD | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: DragonHD. Long form: Available for all selectable voices. |
| Azure | Ultra | Dragon HD Omni | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: DragonHDOmni. Long form: Available for all selectable voices. |
| Azure | Premium | Dragon HD Flash | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: DragonHDFlash. Long form: Available for all selectable voices. |
| Azure | Premium | OpenAI Neural | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: OpenAINeural. Long form: Available for all selectable voices. |
| Azure | Ultra | OpenAI Neural HD | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: OpenAINeuralHD. Long form: Available for all selectable voices. |
| Azure | Ultra | MAI Voice 2 | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: MAIVoice2. Long form: Available for all selectable voices. |
| Azure | Premium | MAI Voice 2 Flash | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: MAIVoice2Flash. Long form: Available for all selectable voices. |
| Azure | Premium | MAI Voice 1 | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: MAIVoice1. Long form: Available for all selectable voices. |
| Azure | Premium | Dragon Latest | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: DragonLatest. Long form: Available for all selectable voices. |
| Azure | Ultra | MAI Voice 2.1 | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: MAIVoice21. Long form: Available for all selectable voices. |
| Azure | Premium | MAI Voice 2.1 Flash | Yes | ogg_opus | alaw (8000 Hz), mp3 (16000 Hz, 24000 Hz, 48000 Hz), mulaw (8000 Hz), ogg_opus (16000 Hz, 24000 Hz, 48000 Hz), pcm (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz), wav (16000 Hz, 22050 Hz, 24000 Hz, 44100 Hz, 48000 Hz, 8000 Hz) | mp3 16000 Hz: 128 kbps, 32 kbps, 64 kbps, mp3 24000 Hz: 160 kbps, 48 kbps, 96 kbps, mp3 48000 Hz: 192 kbps, 96 kbps | Family token: MAIVoice21Flash. Long form: Available for all selectable voices. |
API v1 callers can request any supported format from the matrix above via output_format and sample_rate_hertz. If omitted, the default stream format is used. The /tts web app exposes only the browser-playable subset (ogg_opus, mp3, wav). Bitrate selection depends on the provider and family; use the matrix above for available values. Where supported, preview_transport_format: "pcm" changes only live preview transport while the saved artifact keeps the requested or default WAV, MP3 or Ogg Opus format. Azure MP3 rate and bitrate choices apply to the saved file during PCM preview. Voice detail responses expose stream_bitrates_kbps and supports_pcm_preview for Azure. See API v1 Streaming for request/response details.
Azure family details
This reference lists 13 Azure families. Registered families may be unavailable; check each row's delivery settings. Long-form speech is available for every selectable Azure voice. Select a voice using the public voice_id returned by voice discovery, such as azure:en-US-Neural-Aria.
Style and role values are metadata for caller-authored SSML. The API does not provide structured style controls. Professional custom voice and personal voice cloning are not offered.
| Family | Token | Tier | Formats | Rates | Bitrates | Transports | Long form | Styles | Roles | Input mechanism | Regions | Release |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Standard Neural | Neural | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | advertisement-upbeat, affectionate, angry, assistant, calm, chat, chat-casual, cheerful, conversation, customerservice, depressed, disgruntled, documentary-narration, embarrassed, empathetic, envious, excited, fearful, friendly, gentle, hopeful, livecommercial, lyrical, narration-professional, narration-relaxed, newscast, newscast-casual, newscast-formal, poetry-reading, sad, serious, shouting, sorry, sports-commentary, sports-commentary-excited, terrified, unfriendly, whispering | Boy, Girl, Narrator, OlderAdultFemale, OlderAdultMale, SeniorFemale, SeniorMale, YoungAdultFemale, YoungAdultMale | Caller-authored SSML | eastus, eastus2, northcentralus, swedencentral | eastus: deprecated, eastus: generally-available, eastus: public-preview, eastus2: deprecated, eastus2: generally-available, northcentralus: deprecated, northcentralus: generally-available, swedencentral: deprecated, swedencentral: generally-available |
| Multilingual Neural | Multilingual | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | affectionate, angry, chat, cheerful, cute, empathetic, excited, friendly, funny, poetry-reading, relieved, sad, serious, shy, sorry, story | not available | Caller-authored SSML | eastus, eastus2, northcentralus, swedencentral | eastus: generally-available, eastus: public-preview, eastus2: generally-available, northcentralus: generally-available, swedencentral: generally-available |
| Dragon HD | DragonHD | Ultra | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | not available | not available | not available | eastus, eastus2, swedencentral | eastus: generally-available, eastus: public-preview, eastus2: generally-available, eastus2: public-preview, swedencentral: generally-available, swedencentral: public-preview |
| Dragon HD Omni | DragonHDOmni | Ultra | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | not available | not available | not available | eastus, eastus2, swedencentral | eastus: public-preview, eastus2: public-preview, swedencentral: public-preview |
| Dragon HD Flash | DragonHDFlash | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | affectionate, angry, anxious, assassin, captain, cavalier, chat, cheerful, comforting, complaining, curious, customer-service, cute, debating, depressed, disappointed, empathetic, encouraging, excited, fearful, game-narrator, gentle, geomancer, guilty, live-commercial, lonely, nervous, news, poet, poetry-reading, prince, sad, sentimental, serious, shy, sorry, story-telling, strict, surprised, tired, voice-assistant, whispering | not available | Caller-authored SSML | eastus, eastus2, swedencentral | eastus: generally-available, eastus2: generally-available, swedencentral: generally-available |
| OpenAI Neural | OpenAINeural | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | not available | not available | not available | northcentralus, swedencentral | northcentralus: public-preview, swedencentral: public-preview |
| OpenAI Neural HD | OpenAINeuralHD | Ultra | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | not available | not available | not available | northcentralus, swedencentral | northcentralus: public-preview, swedencentral: public-preview |
| MAI Voice 2 | MAIVoice2 | Ultra | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | adventurous, angry, caringempathy, confused, curious, determined, disgusted, embarrassed, encouraging, excited, fearful, friendlycheerful, happy, hopeful, jealous, joyful, nostalgic, reflective, regretful, relieved, sad, saddisappointed, serious, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML | eastus, eastus2, swedencentral | eastus: public-preview, eastus2: public-preview, swedencentral: public-preview |
| MAI Voice 2 Flash | MAIVoice2Flash | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | adventurous, angry, caringempathy, confused, curious, determined, disgusted, embarrassed, encouraging, excited, fearful, friendlycheerful, happy, hopeful, jealous, joyful, nostalgic, reflective, regretful, relieved, sad, saddisappointed, serious, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML | eastus, eastus2, swedencentral | eastus: public-preview, eastus2: public-preview, swedencentral: public-preview |
| MAI Voice 1 | MAIVoice1 | Premium | wav | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz | not available | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | anger, callcenter, confusion, customerservice, determination, disgust, embarrassment, excitement, fear, generalconversation, happiness, hope, jealous, jealousy, joy, learning, media, narration, neutral, persuasive, professional, regret, relief, sadness, sales, shouting, softvoice, surprise, whispering | not available | Caller-authored SSML | eastus, eastus2, swedencentral | eastus: public-preview, eastus2: public-preview, swedencentral: public-preview |
| Dragon Latest | DragonLatest | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | not available | not available | not available | eastus, eastus2, swedencentral | eastus: public-preview, eastus2: public-preview, swedencentral: public-preview |
| MAI Voice 2.1 | MAIVoice21 | Ultra | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | adventurous, angry, caringempathy, confused, curious, determined, disgusted, embarrassed, encouraging, excited, fearful, friendlycheerful, happy, hopeful, jealous, joyful, nostalgic, reflective, regretful, relieved, sad, saddisappointed, serious, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML | swedencentral | swedencentral: public-preview |
| MAI Voice 2.1 Flash | MAIVoice21Flash | Premium | wav; mp3; ogg_opus | wav: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; mp3: 8 kHz, 12 kHz, 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz; ogg_opus: 8 kHz, 12 kHz, 16 kHz, 24 kHz, 48 kHz | mp3 8 kHz: 32, 64 kbps; mp3 12 kHz: 32, 64 kbps; mp3 16 kHz: 32, 64, 96, 128, 160 kbps; mp3 22.05 kHz: 32, 64, 96, 128, 160 kbps; mp3 24 kHz: 32, 64, 96, 128, 160 kbps; mp3 44.1 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; mp3 48 kHz: 32, 64, 96, 128, 160, 192, 256, 320 kbps; ogg_opus 8 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 12 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 16 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 24 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps; ogg_opus 48 kHz: 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 160, 192, 256 kbps | alaw, mp3, mulaw, ogg_opus, pcm, wav | Available for all selectable voices | adventurous, angry, caringempathy, confused, curious, determined, disgusted, embarrassed, encouraging, excited, fearful, friendlycheerful, happy, hopeful, jealous, joyful, nostalgic, reflective, regretful, relieved, sad, saddisappointed, serious, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML | swedencentral | swedencentral: public-preview |
Generated public voice examples
standard (Neural)
azure:af-ZA-Neural-Adrimultilingual (Multilingual)
azure:af-ZA-Multilingual-Adadragon-hd (DragonHD)
azure:af-ZA-DragonHD-Aartidragon-hd-omni (DragonHDOmni)
azure:af-ZA-DragonHDOmni-Andrewdragon-hd-flash (DragonHDFlash)
azure:en-US-DragonHDFlash-Jimmieopenai-neural (OpenAINeural)
azure:af-ZA-OpenAINeural-Alloyopenai-neural-hd (OpenAINeuralHD)
azure:af-ZA-OpenAINeuralHD-Alloymai-voice-2 (MAIVoice2)
azure:de-DE-MAIVoice2-Alejomai-voice-2-flash (MAIVoice2Flash)
azure:de-DE-MAIVoice2Flash-Alejomai-voice-1 (MAIVoice1)
azure:en-US-MAIVoice1-Grantdragon-latest (DragonLatest)
azure:af-ZA-DragonLatest-Alessiomai-voice-2.1 (MAIVoice21)
azure:cs-CZ-MAIVoice21-Grantmai-voice-2.1-flash (MAIVoice21Flash)
azure:cs-CZ-MAIVoice21Flash-GrantVoice-specific capability exceptions
Each row lists voices whose tier, long form availability, regions, or release status differ from their family default. Style and role vocabularies are listed separately below.
| Family | Voices | Tier | Long form | Regions | Release |
|---|
Style and role vocabularies by voice
Style and role vocabularies are per selectable voice. Each row lists the voices that share one. A voice absent from this table has no published style or role controls. Style degree applies only where the family declares it and a style is selected.
| Family | Voices | Styles | Roles | Input mechanism |
|---|---|---|---|---|
| dragon-hd-flash | zh-CN-Xiaoxiao2:DragonHDFlashLatestNeural | affectionate, angry, anxious, cheerful, curious, disappointed, empathetic, encouraging, excited, fearful, guilty, lonely, poetry-reading, sad, sentimental, sorry, story-telling, surprised, tired, whispering | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Yunxia:DragonHDFlashLatestNeural | affectionate, angry, cheerful, comforting, encouraging, excited, fearful, sad, surprised | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaohan:DragonHDFlashLatestNeural | affectionate, angry, cheerful, complaining, fearful, gentle, sad, shy, strict | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoxiao:DragonHDFlashLatestNeural | angry, chat, cheerful, comforting, customer-service, debating, disappointed, excited, fearful, sad, shy, sorry, strict, voice-assistant, whispering | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Yunxi:DragonHDFlashLatestNeural | angry, chat, cheerful, complaining, depressed, fearful, news, sad, shy, strict, voice-assistant | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoyou:DragonHDFlashLatestNeural | angry, chat, cheerful, cute, poetry-reading, sad, story-telling | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoyu:DragonHDFlashLatestNeural | angry, cheerful, comforting, debating, sad, sorry | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoyi:DragonHDFlashLatestNeural | angry, cheerful, complaining, cute, gentle, nervous, sad, shy, strict | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Yunhan:DragonHDFlashLatestNeural | angry, cheerful, curious, empathetic, encouraging, excited, guilty, lonely, sad, serious, sorry, surprised, tired, whispering | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoqi:DragonHDFlashLatestNeural | angry, cheerful, customer-service, excited, fearful, sad, sorry, whispering | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoke:DragonHDFlashLatestNeural | angry, customer-service, cute, excited, fearful, sad, sorry, whispering | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Yunyi:DragonHDFlashLatestNeural | assassin, captain, cavalier, game-narrator, geomancer, poet, prince | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaoshuang:DragonHDFlashLatestNeural | chat | not available | Caller-authored SSML |
| dragon-hd-flash | zh-CN-Xiaochen:DragonHDFlashLatestNeural | cheerful, debating, empathetic, live-commercial, poetry-reading, sad, sorry | not available | Caller-authored SSML |
| mai-voice-1 | en-US-June:MAI-Voice-1 | anger, callcenter, confusion, customerservice, disgust, embarrassment, fear, generalconversation, happiness, jealous, joy, learning, professional, regret, sadness, surprise | not available | Caller-authored SSML |
| mai-voice-1 | en-US-Iris:MAI-Voice-1 | anger, confusion, determination, disgust, embarrassment, excitement, fear, generalconversation, happiness, hope, jealousy, joy, narration, neutral, regret, relief, sadness, shouting, softvoice, surprise, whispering | not available | Caller-authored SSML |
| mai-voice-1 | en-US-Grant:MAI-Voice-1 | anger, confusion, determination, disgust, embarrassment, excitement, fear, generalconversation, happiness, hope, jealousy, joy, neutral, professional, regret, relief, sadness, shouting, softvoice, surprise, whispering | not available | Caller-authored SSML |
| mai-voice-1 | en-US-Jasper:MAI-Voice-1 | anger, confusion, disgust, embarrassment, excitement, fear, generalconversation, happiness, hope, jealous, joy, learning, media, persuasive, regret, sadness, sales, surprise | not available | Caller-authored SSML |
| mai-voice-2-flash | es-ES-Marta:MAI-Voice-2-Flash, nl-NL-Sander:MAI-Voice-2-Flash, ru-RU-Lev:MAI-Voice-2-Flash, ru-RU-Masha:MAI-Voice-2-Flash, th-TH-Krit:MAI-Voice-2-Flash, th-TH-Nattapong:MAI-Voice-2-Flash, tr-TR-Aydın:MAI-Voice-2-Flash, tr-TR-Elif:MAI-Voice-2-Flash | adventurous, caringempathy, curious, encouraging, excited, friendlycheerful, nostalgic, reflective, saddisappointed, serious | not available | Caller-authored SSML |
| mai-voice-2-flash | de-DE-Klaus:MAI-Voice-2-Flash, de-DE-Mia:MAI-Voice-2-Flash, en-AU-Isla:MAI-Voice-2-Flash, en-US-Ethan:MAI-Voice-2-Flash, en-US-Olivia:MAI-Voice-2-Flash, es-MX-Alejo:MAI-Voice-2-Flash, es-MX-Valeria:MAI-Voice-2-Flash, fr-FR-Marc:MAI-Voice-2-Flash, fr-FR-Soleil:MAI-Voice-2-Flash, hi-IN-Dhruv:MAI-Voice-2-Flash, hi-IN-Kavya:MAI-Voice-2-Flash, hi-IN-Priya:MAI-Voice-2-Flash, it-IT-Luca:MAI-Voice-2-Flash, it-IT-Rosa:MAI-Voice-2-Flash, pt-BR-Caio:MAI-Voice-2-Flash, pt-BR-Luana:MAI-Voice-2-Flash, zh-CN-Bo:MAI-Voice-2-Flash, zh-CN-Mei:MAI-Voice-2-Flash | angry, confused, determined, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, relieved, sad, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML |
| mai-voice-2-flash | en-US-Harper:MAI-Voice-2-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, shouting, softvoice, whispering | not available | Caller-authored SSML |
| mai-voice-2-flash | ko-KR-Haena:MAI-Voice-2-Flash, pt-BR-Rafael:MAI-Voice-2-Flash, pt-PT-Rui:MAI-Voice-2-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2-flash | ko-KR-Junho:MAI-Voice-2-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, relieved, sad, softvoice | not available | Caller-authored SSML |
| mai-voice-2-flash | hi-IN-Arjun:MAI-Voice-2-Flash, zh-CN-Wei:MAI-Voice-2-Flash | angry, confused, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2-flash | zh-CN-Lan:MAI-Voice-2-Flash | angry, confused, disgusted, embarrassed, excited, fearful, happy, joyful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2-flash | pt-BR-Pedro:MAI-Voice-2-Flash | confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2 | es-ES-Marta:MAI-Voice-2, nl-NL-Sander:MAI-Voice-2, ru-RU-Lev:MAI-Voice-2, ru-RU-Masha:MAI-Voice-2, th-TH-Krit:MAI-Voice-2, th-TH-Nattapong:MAI-Voice-2, tr-TR-Aydın:MAI-Voice-2, tr-TR-Elif:MAI-Voice-2 | adventurous, caringempathy, curious, encouraging, excited, friendlycheerful, nostalgic, reflective, saddisappointed, serious | not available | Caller-authored SSML |
| mai-voice-2 | de-DE-Klaus:MAI-Voice-2, de-DE-Mia:MAI-Voice-2, en-AU-Isla:MAI-Voice-2, en-US-Ethan:MAI-Voice-2, en-US-Olivia:MAI-Voice-2, es-MX-Alejo:MAI-Voice-2, es-MX-Valeria:MAI-Voice-2, fr-FR-Marc:MAI-Voice-2, fr-FR-Soleil:MAI-Voice-2, hi-IN-Dhruv:MAI-Voice-2, hi-IN-Kavya:MAI-Voice-2, hi-IN-Priya:MAI-Voice-2, it-IT-Luca:MAI-Voice-2, it-IT-Rosa:MAI-Voice-2, pt-BR-Caio:MAI-Voice-2, pt-BR-Luana:MAI-Voice-2, zh-CN-Bo:MAI-Voice-2, zh-CN-Mei:MAI-Voice-2 | angry, confused, determined, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, relieved, sad, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML |
| mai-voice-2 | en-US-Harper:MAI-Voice-2 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, shouting, softvoice, whispering | not available | Caller-authored SSML |
| mai-voice-2 | ko-KR-Haena:MAI-Voice-2, pt-BR-Rafael:MAI-Voice-2, pt-PT-Rui:MAI-Voice-2 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2 | ko-KR-Junho:MAI-Voice-2 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, relieved, sad, softvoice | not available | Caller-authored SSML |
| mai-voice-2 | hi-IN-Arjun:MAI-Voice-2, zh-CN-Wei:MAI-Voice-2 | angry, confused, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2 | zh-CN-Lan:MAI-Voice-2 | angry, confused, disgusted, embarrassed, excited, fearful, happy, joyful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2 | pt-BR-Pedro:MAI-Voice-2 | confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2.1-flash | es-ES-Marta:MAI-Voice-2.1-Flash, nl-NL-Sander:MAI-Voice-2.1-Flash, ru-RU-Lev:MAI-Voice-2.1-Flash, ru-RU-Masha:MAI-Voice-2.1-Flash, th-TH-Krit:MAI-Voice-2.1-Flash, th-TH-Nattapong:MAI-Voice-2.1-Flash, tr-TR-Aydin:MAI-Voice-2.1-Flash, tr-TR-Elif:MAI-Voice-2.1-Flash | adventurous, caringempathy, curious, encouraging, excited, friendlycheerful, nostalgic, reflective, saddisappointed, serious | not available | Caller-authored SSML |
| mai-voice-2.1-flash | de-DE-Klaus:MAI-Voice-2.1-Flash, de-DE-Mia:MAI-Voice-2.1-Flash, en-AU-Lisa:MAI-Voice-2.1-Flash, en-US-Ethan:MAI-Voice-2.1-Flash, en-US-Olivia:MAI-Voice-2.1-Flash, es-MX-Alejo:MAI-Voice-2.1-Flash, es-MX-Valeria:MAI-Voice-2.1-Flash, fr-FR-Marc:MAI-Voice-2.1-Flash, fr-FR-Soleil:MAI-Voice-2.1-Flash, hi-IN-Dhruv:MAI-Voice-2.1-Flash, hi-IN-Kavya:MAI-Voice-2.1-Flash, hi-IN-Priya:MAI-Voice-2.1-Flash, it-IT-Luca:MAI-Voice-2.1-Flash, it-IT-Rosa:MAI-Voice-2.1-Flash, pt-BR-Caio:MAI-Voice-2.1-Flash, pt-BR-Luana:MAI-Voice-2.1-Flash, zh-CN-Bo:MAI-Voice-2.1-Flash, zh-CN-Mei:MAI-Voice-2.1-Flash | angry, confused, determined, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, relieved, sad, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML |
| mai-voice-2.1-flash | en-US-Harper:MAI-Voice-2.1-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, shouting, softvoice, whispering | not available | Caller-authored SSML |
| mai-voice-2.1-flash | ko-KR-Hana:MAI-Voice-2.1-Flash, pt-BR-Rafael:MAI-Voice-2.1-Flash, pt-PT-Rui:MAI-Voice-2.1-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2.1-flash | ko-KR-Junho:MAI-Voice-2.1-Flash | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, relieved, sad, softvoice | not available | Caller-authored SSML |
| mai-voice-2.1-flash | hi-IN-Arjun:MAI-Voice-2.1-Flash | angry, confused, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2.1-flash | zh-CN-Lan:MAI-Voice-2.1-Flash | angry, confused, disgusted, embarrassed, excited, fearful, happy, joyful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2.1-flash | pt-BR-Pedro:MAI-Voice-2.1-Flash | confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2.1 | es-ES-Marta:MAI-Voice-2.1, nl-NL-Sander:MAI-Voice-2.1, ru-RU-Lev:MAI-Voice-2.1, ru-RU-Masha:MAI-Voice-2.1, th-TH-Krit:MAI-Voice-2.1, th-TH-Nattapong:MAI-Voice-2.1, tr-TR-Aydin:MAI-Voice-2.1, tr-TR-Elif:MAI-Voice-2.1 | adventurous, caringempathy, curious, encouraging, excited, friendlycheerful, nostalgic, reflective, saddisappointed, serious | not available | Caller-authored SSML |
| mai-voice-2.1 | de-DE-Klaus:MAI-Voice-2.1, de-DE-Mia:MAI-Voice-2.1, en-AU-Lisa:MAI-Voice-2.1, en-US-Ethan:MAI-Voice-2.1, en-US-Olivia:MAI-Voice-2.1, es-MX-Alejo:MAI-Voice-2.1, es-MX-Valeria:MAI-Voice-2.1, fr-FR-Marc:MAI-Voice-2.1, fr-FR-Soleil:MAI-Voice-2.1, hi-IN-Dhruv:MAI-Voice-2.1, hi-IN-Kavya:MAI-Voice-2.1, hi-IN-Priya:MAI-Voice-2.1, it-IT-Luca:MAI-Voice-2.1, it-IT-Rosa:MAI-Voice-2.1, pt-BR-Caio:MAI-Voice-2.1, pt-BR-Luana:MAI-Voice-2.1, zh-CN-Bo:MAI-Voice-2.1, zh-CN-Mei:MAI-Voice-2.1 | angry, confused, determined, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, relieved, sad, shouting, softvoice, surprised, whispering | not available | Caller-authored SSML |
| mai-voice-2.1 | en-US-Harper:MAI-Voice-2.1 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, shouting, softvoice, whispering | not available | Caller-authored SSML |
| mai-voice-2.1 | ko-KR-Hana:MAI-Voice-2.1, pt-BR-Rafael:MAI-Voice-2.1, pt-PT-Rui:MAI-Voice-2.1 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| mai-voice-2.1 | ko-KR-Junho:MAI-Voice-2.1 | angry, confused, determined, embarrassed, excited, happy, hopeful, joyful, relieved, sad, softvoice | not available | Caller-authored SSML |
| mai-voice-2.1 | hi-IN-Arjun:MAI-Voice-2.1 | angry, confused, disgusted, embarrassed, excited, fearful, happy, hopeful, jealous, joyful, regretful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2.1 | zh-CN-Lan:MAI-Voice-2.1 | angry, confused, disgusted, embarrassed, excited, fearful, happy, joyful, sad, surprised | not available | Caller-authored SSML |
| mai-voice-2.1 | pt-BR-Pedro:MAI-Voice-2.1 | confused, determined, embarrassed, excited, happy, hopeful, joyful, regretful, relieved, sad, softvoice, surprised | not available | Caller-authored SSML |
| multilingual | zh-CN-XiaoxiaoMultilingualNeural | affectionate, cheerful, empathetic, excited, poetry-reading, sorry, story | not available | Caller-authored SSML |
| multilingual | zh-CN-XiaoyouMultilingualNeural | angry, chat, cheerful, cute, poetry-reading, sad, story | not available | Caller-authored SSML |
| multilingual | zh-CN-XiaoshuangMultilingualNeural | chat | not available | Caller-authored SSML |
| multilingual | en-US-SerenaMultilingualNeural | empathetic, excited, friendly, relieved, sad, serious, shy | not available | Caller-authored SSML |
| multilingual | en-US-DerekMultilingualNeural | empathetic, excited, relieved, shy | not available | Caller-authored SSML |
| multilingual | en-US-DavisMultilingualNeural | empathetic, funny, relieved | not available | Caller-authored SSML |
| multilingual | en-US-AndrewMultilingualNeural | empathetic, relieved | not available | Caller-authored SSML |
| multilingual | en-US-PhoebeMultilingualNeural | empathetic, sad, serious | not available | Caller-authored SSML |
| multilingual | en-US-NancyMultilingualNeural | excited, friendly, funny, relieved, shy | not available | Caller-authored SSML |
| standard | zh-CN-YunhaoNeural | advertisement-upbeat | not available | Caller-authored SSML |
| standard | zh-CN-XiaoxiaoNeural | affectionate, angry, assistant, calm, chat, chat-casual, cheerful, customerservice, disgruntled, excited, fearful, friendly, gentle, lyrical, newscast, poetry-reading, sad, serious, sorry, whispering | not available | Caller-authored SSML |
| standard | zh-CN-XiaomoNeural | affectionate, angry, calm, cheerful, depressed, disgruntled, embarrassed, envious, fearful, gentle, sad, serious | Boy, Girl, OlderAdultFemale, OlderAdultMale, SeniorFemale, SeniorMale, YoungAdultFemale, YoungAdultMale | Caller-authored SSML |
| standard | zh-CN-XiaohanNeural | affectionate, angry, calm, cheerful, disgruntled, embarrassed, fearful, gentle, sad, serious | not available | Caller-authored SSML |
| standard | zh-CN-XiaoyiNeural | affectionate, angry, cheerful, disgruntled, embarrassed, fearful, gentle, sad, serious | not available | Caller-authored SSML |
| standard | en-US-JennyNeural | angry, assistant, chat, cheerful, customerservice, excited, friendly, hopeful, newscast, sad, shouting, terrified, unfriendly, whispering | not available | Caller-authored SSML |
| standard | zh-CN-YunxiNeural | angry, assistant, chat, cheerful, depressed, disgruntled, embarrassed, fearful, narration-relaxed, newscast, sad, serious | Boy, Narrator, YoungAdultMale | Caller-authored SSML |
| standard | zh-CN-YunzeNeural | angry, calm, cheerful, depressed, disgruntled, documentary-narration, fearful, sad, serious | OlderAdultMale, SeniorMale | Caller-authored SSML |
| standard | zh-CN-YunyeNeural | angry, calm, cheerful, disgruntled, embarrassed, fearful, sad, serious | Boy, Girl, OlderAdultFemale, OlderAdultMale, SeniorFemale, SeniorMale, YoungAdultFemale, YoungAdultMale | Caller-authored SSML |
| standard | zh-CN-YunxiaNeural | angry, calm, cheerful, fearful, sad | not available | Caller-authored SSML |
| standard | zh-CN-XiaoruiNeural | angry, calm, fearful, sad | not available | Caller-authored SSML |
| standard | en-US-AriaNeural | angry, chat, cheerful, customerservice, empathetic, excited, friendly, hopeful, narration-professional, newscast-casual, newscast-formal, sad, shouting, terrified, unfriendly, whispering | not available | Caller-authored SSML |
| standard | en-US-DavisNeural | angry, chat, cheerful, excited, friendly, hopeful, sad, shouting, terrified, unfriendly, whispering | not available | Caller-authored SSML |
| standard | zh-CN-YunjianNeural | angry, cheerful, depressed, disgruntled, documentary-narration, narration-relaxed, sad, serious, sports-commentary, sports-commentary-excited | not available | Caller-authored SSML |
| standard | zh-CN-YunfengNeural | angry, cheerful, depressed, disgruntled, fearful, sad, serious | not available | Caller-authored SSML |
| standard | zh-CN-XiaozhenNeural | angry, cheerful, disgruntled, fearful, sad, serious | not available | Caller-authored SSML |
| standard | en-US-GuyNeural | angry, cheerful, excited, friendly, hopeful, newscast, sad, shouting, terrified, unfriendly, whispering | not available | Caller-authored SSML |
| standard | en-US-JaneNeural, en-US-JasonNeural, en-US-NancyNeural, en-US-SaraNeural, en-US-TonyNeural | angry, cheerful, excited, friendly, hopeful, sad, shouting, terrified, unfriendly, whispering | not available | Caller-authored SSML |
| standard | en-US-AvaNeural | angry, fearful, sad | not available | Caller-authored SSML |
| standard | pt-BR-FranciscaNeural | calm | not available | Caller-authored SSML |
| standard | ja-JP-NanamiNeural | chat, cheerful, customerservice | not available | Caller-authored SSML |
| standard | en-GB-RyanNeural, es-MX-JorgeNeural, it-IT-IsabellaNeural | chat, cheerful | not available | Caller-authored SSML |
| standard | zh-CN-XiaomengNeural, zh-CN-XiaoshuangNeural | chat | not available | Caller-authored SSML |
| standard | en-IN-NeerjaNeural, hi-IN-SwaraNeural | cheerful, empathetic, newscast | not available | Caller-authored SSML |
| standard | en-GB-SoniaNeural, fr-FR-DeniseNeural, fr-FR-HenriNeural | cheerful, sad | not available | Caller-authored SSML |
| standard | de-DE-ConradNeural | cheerful | not available | Caller-authored SSML |
| standard | en-US-KaiNeural, en-US-LunaNeural | conversation | not available | Caller-authored SSML |
| standard | zh-CN-YunyangNeural | customerservice, narration-professional, newscast-casual | not available | Caller-authored SSML |
| standard | zh-CN-XiaochenNeural | livecommercial | not available | Caller-authored SSML |
Back to Documentation
© 2026 AI TTS Microservice. All rights reserved.