switchboard
F

Fish Audio

by Fish Audio

Generates speech, clones voices and transcribes audio through REST and WebSocket APIs backed by open-weight models, for developers building voice apps and phone agents.

5
Skills
API Key
Auth
Yes
Streaming
No
Push

Skills

Text to Speech

Converts text to speech with emotion tags and fine-grained pronunciation control, over REST or real-time WebSocket.

Voice Cloning

Creates reusable custom voice models from reference audio.

Speech to Text

Transcribes audio, including multi-speaker conversations with speaker turns.

Voice Design

Generates candidate voices from a natural-language prompt.

Voice Agent Platform

Builds voice agents with knowledge bases, webhook tools and phone numbers, deployable via web SDK or widget.

Voice & MessagingContent & Mediatext-to-speechvoice-cloningspeech-to-textvoice-designwebsocket-streamingopen-weights
Visit Agent

Related Agents

C

Cartesia

Delivers ultra-low-latency text-to-speech and speech-to-text through the Sonic model family, with a voice-agent framewo…

Voice & Messaging
API
3 skillsAPI Key
V

Voicebox

Runs a local voice studio for voice cloning, text-to-speech and Whisper dictation, and lets agents speak or transcribe…

Voice & Messaging
MCPAPI
4 skillsNone
C

Clipto MCP

Indexes terabytes of local video, audio, and images so agents can search them in natural language and pull back timesta…

Content & MediaResearch & Knowledge
MCP
3 skillsNone
D

Docling

Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, D…

Content & MediaData & Analytics
APICLIMCP
5 skillsNone
fish-audio
Generates speech, clones voices and transcribes audio through REST and WebSocket APIs backed by open-weight models, for developers building voice apps and phone agents.
fields
nameFish Audio
providerFish Audio
urlhttps://fish.audio
categoriesvoice-messaging · content-media
accessapi
authapiKey
streamingtrue
pushfalse
verifiedtrue
officialfalse
tagstext-to-speech, voice-cloning, speech-to-text, voice-design, websocket-streaming, open-weights
skills
text-to-speechText to SpeechConverts text to speech with emotion tags and fine-grai…
voice-cloningVoice CloningCreates reusable custom voice models from reference aud…
speech-to-textSpeech to TextTranscribes audio, including multi-speaker conversation…
voice-designVoice DesignGenerates candidate voices from a natural-language prom…
voice-agent-platformVoice Agent PlatformBuilds voice agents with knowledge bases, webhook tools…
→ https://fish.audio