> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.jambonz.org/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.jambonz.org/_mcp/server. # TTS Vendor Settings Most TTS vendors expose knobs that go beyond picking a voice — speaking rate, expressiveness, stability, and so on. jambonz passes these through untouched in `synthesizer.options`. ```json { "verb": "say", "text": "Thanks for calling, how can I help you today?", "synthesizer": { "vendor": "cartesia", "language": "en", "voice": "a0e99841-438c-4a64-b679-ae501e7d6091", "options": { "speed": -0.3, "emotion": "positivity:high" } } } ``` The fields `options` accepts are defined entirely by the vendor — jambonz does not validate them. See each vendor's page below for what it supports. ## Where settings can be set There are two places, and they combine: 1. **On the speech credential**, under **Extra Options** in the portal (**Account → Speech →** your credential). These apply to every request using that credential. 2. **On the verb**, in `synthesizer.options`. These apply to that verb only. Where both are present, **the verb wins**. Setting them on the credential is the better default when you want one consistent voice character across an application. Use the verb when a particular prompt needs to differ — a slower, clearer reading of an account number, for example. > **Note** > > Options are passed to the vendor as-is. If you send a field a vendor doesn't recognise, most vendors ignore it silently rather than returning an error — so a typo usually shows up as "my setting had no effect", not as a failure. ## Vendors with settings #### [AssemblyAI](/guides/features/tts-vendor-settings/assembly-ai) Library and cloned voices, EU region, session timeout. #### [Async](/guides/features/tts-vendor-settings/async) Flash and Pro models, fifteen languages, speed and stability. #### [Azure OpenAI](/guides/features/tts-vendor-settings/azure-open-ai) OpenAI voices on your own Azure deployment, speed, spoken instructions. #### [Bland AI](/guides/features/tts-vendor-settings/bland-ai) Voice UUIDs, expressiveness and stability controls. #### [Camb.ai](/guides/features/tts-vendor-settings/camb-ai) MARS voices, speaking rate, enhancement, inference tuning. #### [Cartesia](/guides/features/tts-vendor-settings/cartesia) Speaking rate and emotion, with model-family differences. #### [ElevenLabs](/guides/features/tts-vendor-settings/eleven-labs) Stability, similarity boost, style, speaker boost, latency optimisation. #### [Fish Audio](/guides/features/tts-vendor-settings/fish-audio) Cloned voices, latency mode, speed and volume. #### [Giggy](/guides/features/tts-vendor-settings/giggy) Speaking rate and a seed for repeatable output. #### [Gnani](/guides/features/tts-vendor-settings/gnani) Indic and Indian English Timbre voices, speed, language. #### [Google](/guides/features/tts-vendor-settings/google) Gemini TTS model and prompt. #### [Gradium](/guides/features/tts-vendor-settings/gradium) Temperature, voice similarity, speaking rate, pronunciation dictionaries. #### [Groq](/guides/features/tts-vendor-settings/groq) Orpheus voices for English and Saudi Arabic, speed, sample rate. #### [Hume](/guides/features/tts-vendor-settings/hume) Octave voices, acting directions, speed, trailing silence. #### [Inworld](/guides/features/tts-vendor-settings/inworld) Pitch, speaking rate, temperature. #### [Kokoro](/guides/features/tts-vendor-settings/kokoro) Self-hosted, OpenAI-compatible; speed, volume, voice mixing, text normalization. #### [KugelAudio](/guides/features/tts-vendor-settings/kugel-audio) Speed, guidance scale, temperature, normalization, pronunciation dictionaries. #### [MiniMax](/guides/features/tts-vendor-settings/mini-max) Multilingual voices, emotion, speed, volume, pitch, voice effects, pronunciation dictionaries. #### [Mistral](/guides/features/tts-vendor-settings/mistral) Voxtral preset and cloned voices, expressiveness, emotion tags, pronunciation hints. #### [Murf](/guides/features/tts-vendor-settings/murf) Style, rate, pitch, variation. #### [Neuphonic](/guides/features/tts-vendor-settings/neuphonic) Multilingual voices, speed, temperature, IPA dialect. #### [Paxa Labs](/guides/features/tts-vendor-settings/paxa-labs) Thai, English and Mandarin voices, direction tags, speed, reading language. #### [Resemble](/guides/features/tts-vendor-settings/resemble) Project selection and HD synthesis. #### [Respeecher](/guides/features/tts-vendor-settings/respeecher) Real-time models per language, sampling controls. #### [Rime Labs](/guides/features/tts-vendor-settings/rime-labs) Speed, latency reduction, and per-model sampling controls. #### [Sarvam AI](/guides/features/tts-vendor-settings/sarvam-ai) Indic and Indian English voices, pace, pitch, loudness, temperature, pronunciation dictionaries. #### [Simplismart](/guides/features/tts-vendor-settings/simplismart) Orpheus, Veena and Qwen 3 TTS models, sampling controls, dedicated deployments. #### [Smallest AI](/guides/features/tts-vendor-settings/smallest-ai) Lightning voices, speed, number and date reading, pronunciation dictionaries, content filter. #### [Soniox](/guides/features/tts-vendor-settings/soniox) Voices in sixty languages, speed, silence reduction, regional hosts, same key as Soniox STT. #### [Speechify](/guides/features/tts-vendor-settings/speechify) Loudness and text normalization, model selection. #### [Speechmatics](/guides/features/tts-vendor-settings/speechmatics) British and American English preview voices, same key as Speechmatics STT. #### [Spitch](/guides/features/tts-vendor-settings/spitch) English and African-language voices, speed. #### [Svara](/guides/features/tts-vendor-settings/svara) Speed, pronunciation dictionaries, eager streaming, sampling controls. #### [Vakyam](/guides/features/tts-vendor-settings/vakyam) Indian English and seven Indic languages, speed. #### [xAI](/guides/features/tts-vendor-settings/x-ai) Speed, latency optimisation, text normalization. Vendors not listed here take no options beyond voice, language and model. ## Fallback vendors `synthesizer.options` applies to the primary vendor only. If you configure a `fallbackVendor`, it is used with its own credential-level Extra Options — the primary vendor's `options` are not carried over, since the two vendors' options are unrelated.